© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41132
    Prev
    Next
    INDEX
    Explanations

    prefix indicating 'before', 'in front of', or 'president'

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on the common word stem for “chairperson/ president” (e.g. “před-” in Czech/Slovak, “priekš-” in Latvian, “Πρόεδρος” in Greek, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "
    -2.98
    in
    -2.94
      
    -2.83
    -
    -2.56
    .
    -2.56
    <i>
    -2.50
     $
    -2.41
             
    -2.41
    <b>
    -2.34
     I
    -2.33
    POSITIVE LOGITS
     sanitarias
    2.77
    ㍉
    2.69
     financieras
    2.67
    
    2.61
    ᚺ
    2.55
    咘
    2.50
    骉
    2.50
    脔
    2.45
    傒
    2.45
    メリカ
    2.44
    Activations Density 0.006%

    No Known Activations